hWdZddlZddlZddlZddlmZddlmZmZm Z m Z m Z ddl Z ddl ZddlZddlmZmZddlmZddlmZddlmZdd lmZmZmZmZmZmZm Z dd l!m"Z"m#Z#dd l$m%Z%dd l&m'Z'm(Z(d Z)GddZ*y)ar Run prediction on images, videos, directories, globs, YouTube, webcam, streams, etc. Usage - sources: $ yolo mode=predict model=yolo11n.pt source=0 # webcam img.jpg # image vid.mp4 # video screen # screenshot path/ # directory list.txt # list of images list.streams # list of streams 'path/*.jpg' # glob 'https://youtu.be/LNwODJXcvt4' # YouTube 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP, TCP stream Usage - formats: $ yolo mode=predict model=yolo11n.pt # PyTorch yolo11n.torchscript # TorchScript yolo11n.onnx # ONNX Runtime or OpenCV DNN with dnn=True yolo11n_openvino_model # OpenVINO yolo11n.engine # TensorRT yolo11n.mlpackage # CoreML (macOS-only) yolo11n_saved_model # TensorFlow SavedModel yolo11n.pb # TensorFlow GraphDef yolo11n.tflite # TensorFlow Lite yolo11n_edgetpu.tflite # TensorFlow Edge TPU yolo11n_paddle_model # PaddlePaddle yolo11n.mnn # MNN yolo11n_ncnn_model # NCNN yolo11n_imx_model # Sony IMX yolo11n_rknn_model # Rockchip RKNN N)Path)AnyDictListOptionalUnion)get_cfg get_save_dir)load_inference_source) LetterBox) AutoBackend) DEFAULT_CFGLOGGERMACOSWINDOWS callbackscolorstrops) check_imgsz check_imshow)increment_path) select_devicesmart_inference_modea inference results will accumulate in RAM unless `stream=True` is passed, causing potential out-of-memory errors for large sources or long-running streams and videos. See https://docs.ultralytics.com/modes/predict/ for help. Example: results = model(source=..., stream=True) # generator of Results objects for r in results: boxes = r.boxes # Boxes object for bbox outputs masks = r.masks # Masks object for segment masks outputs probs = r.probs # Class probabilities for classification outputs c eZdZdZeddfdeeeefdeeee e ffdZ de e je ej fde jfdZde jfd Zde ej de ej fd Zd Zdd efd Zd dZdZed dZd!defdZdedede jde edef dZd"dedefdZd#defdZ defdZ!dede fdZ"y)$ BasePredictora  A base class for creating predictors. This class provides the foundation for prediction functionality, handling model setup, inference, and result processing across various input sources. Attributes: args (SimpleNamespace): Configuration for the predictor. save_dir (Path): Directory to save results. done_warmup (bool): Whether the predictor has finished setup. model (torch.nn.Module): Model used for prediction. data (dict): Data configuration. device (torch.device): Device used for prediction. dataset (Dataset): Dataset used for prediction. vid_writer (Dict[str, cv2.VideoWriter]): Dictionary of {save_path: video_writer} for saving video output. plotted_img (np.ndarray): Last plotted image. source_type (SimpleNamespace): Type of input source. seen (int): Number of images processed. windows (List[str]): List of window names for visualization. batch (tuple): Current batch data. results (List[Any]): Current batch results. transforms (callable): Image transforms for classification. callbacks (Dict[str, List[callable]]): Callback functions for different events. txt_path (Path): Path to save text results. _lock (threading.Lock): Lock for thread-safe inference. Methods: preprocess: Prepare input image before inference. inference: Run inference on a given image. postprocess: Process raw predictions into structured results. predict_cli: Run prediction for command line interface. setup_source: Set up input source and inference mode. stream_inference: Stream inference on input source. setup_model: Initialize and configure the model. write_results: Write inference results to files. save_predicted_images: Save prediction visualizations. show: Display results in a window. run_callbacks: Execute registered callbacks for an event. add_callback: Register a new callback function. N overrides _callbacksct|||_t|j|_|jjd|j_d|_|jj rtd|j_d|_|jj|_ d|_ d|_ d|_ i|_ d|_d|_d|_g|_d|_d|_d|_|xst+j,|_d|_t1j2|_t+j6|y)a* Initialize the BasePredictor class. Args: cfg (str | dict): Path to a configuration file or a configuration dictionary. overrides (dict, optional): Configuration overrides. _callbacks (dict, optional): Dictionary of callback functions. Ng?FT)warnr)r argsr save_dirconf done_warmupshowrmodeldataimgszdevicedataset vid_writer plotted_img source_typeseenwindowsbatchresults transformsrget_default_callbackstxt_path threadingLock_lockadd_integration_callbacks)selfcfgrrs Z/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/ultralytics/engine/predictor.py__init__zBasePredictor.__init__msC+ $TYY/ 99>> !!DIIN  99>>)t4DIIN IINN        #Hy'F'F'H ^^% ++D1imreturnct|tj }|r{tj|j |}|j ddk(r |ddddf}|jd}tj|}tj|}|j|j}|jjr|jn|j}|r|dz}|S)a Prepare input image before inference. Args: im (torch.Tensor | List[np.ndarray]): Images of shape (N, 3, H, W) for tensor, [(H, W, 3) x N] for list. Returns: (torch.Tensor): Preprocessed image tensor of shape (N, 3, H, W). .N)rrA) isinstancetorchTensornpstack pre_transformshape transposeascontiguousarray from_numpytor(r%fp16halffloat)r8r= not_tensors r: preprocesszBasePredictor.preprocesss$B 55 $,,R01Bxx|q TrT ]l+B%%b)B!!"%B UU4;; **//RWWYrxxz  #IB r<c\|jjrS|jjs=t |j t |jddjz dnd}|j|g||jj||jjd|S)zGRun inference on a given image using the specified model and arguments.rT)mkdirF)augment visualizeembed) r rXr,tensorrr!rr/stemr%rWrY)r8r=r kwargsrXs r: inferencezBasePredictor.inferencesyy""D,<,<,C,C 4==4 1 a0@+A+F+FFd S  tzz"ufjudii&7&79TXT]T]TcTcuntuur<ct|Dchc]}|jc}dk(}t|j|xr`|jj xrH|j jxs0t|j ddxr|j j |j j}|Dcgc] }|| c}Scc}wcc}w)z Pre-transform input image before inference. Args: im (List[np.ndarray]): List of images with shape [(H, W, 3) x N]. Returns: (List[np.ndarray]): List of transformed images. rBdynamicF)autostride)image) lenrKr r'r rectr%ptgetattrimxra)r8r=x same_shapes letterboxs r:rJzBasePredictor.pre_transformsB/q177/0A5  JJb b`74::y%#H#_QUQ[Q[Q_Q_M_::$$  -//q "//00s C 9Cc|S)z6Post-process predictions for an image and return them.)r8predsimg orig_imgss r: postprocesszBasePredictor.postprocesss r<streamc||_|r|j||g|i|St|j||g|i|S)a Perform inference on an image or stream. Args: source (str | Path | List[str] | List[Path] | List[np.ndarray] | np.ndarray | torch.Tensor, optional): Source for inference. model (str | Path | torch.nn.Module, optional): Model for inference. stream (bool): Whether to stream the inference results. If True, returns a generator. *args (Any): Additional arguments for the inference method. **kwargs (Any): Additional keyword arguments for the inference method. Returns: (List[ultralytics.engine.results.Results] | generator): Results objects or generator of Results objects. )rqstream_inferencelist)r8sourcer%rqr r\s r:__call__zBasePredictor.__call__sR (4((HHH H---feMdMfMN Nr<c6|j||}|D]}y)aD Method used for Command Line Interface (CLI) prediction. This function is designed to run predictions using the CLI. It sets up the source and model, then processes the inputs in a streaming manner. This method ensures that no outputs accumulate in memory by consuming the generator without storing results. Args: source (str | Path | List[str] | List[Path] | List[np.ndarray] | np.ndarray | torch.Tensor, optional): Source for inference. model (str | Path | torch.nn.Module, optional): Model for inference. Note: Do not modify this function or remove the generator. The generator ensures that no outputs are accumulated in memory, which is critical for preventing memory issues during long-running predictions. N)rs)r8rur%gen_s r: predict_clizBasePredictor.predict_clis("##FE2 A  r<c t|jj|jjd|_t ||jj |jj|jjt|jdd|_ |jj|_ t|dds~|jjsO|jjs9t|jdkDs!tt|jd d grt!j"t$i|_y ) z Set up source and inference mode. Args: source (str | Path | List[str] | List[Path] | List[np.ndarray] | np.ndarray | torch.Tensor): Source for inference. rC)ramin_dimchrA)rur/ vid_stridebufferchannelsrqTi video_flagFN)rr r'r%rar r/r~ stream_bufferrfr)r,rq screenshotrcanyrwarningSTREAM_WARNINGr*)r8rus r: setup_sourcezBasePredictor.setup_sources!9J9JTUV ,))//yy++99**TZZq1    <<33tXt,    # #**4<< 4'74<<w?@ NN> *r<c /r Kjjrtjdjsj |j 5j||njjjjsjjrBjjrjdz n jjddjsjjjjsjj rdnj"j$jj&gj(d_ dgdc___t1j2j4 t1j2j4 t1j2j4 f}j7d j"D]Q_j7d j.\}}}|d5j9|} ddd|d5j: g|i|} jj<r1t?| t@jBr| gn| Ed{ ddd ddd|d 5jE  |_#dddj7d tI|} tK| D]} xj*dz c_|djLdz| z |djLdz| z |d jLdz| z djF| _'jjsCjjs-jjsjjPs|| xxjS| tU||  |z cc< jjr$tjdjY|j7djFEd{TdddjZj]D]-} t?| t^j`s| jc/jjPrt_jdjjrj*r~tgfdD}tjdtijj.j*tkjddg jld d|zjjs,jjsjjnrtItqjjsd}jjrd|dd|dkDzdjdz nd}tjdtudj|j7dy#1swYxYw7#1swYxYw#1swYxYw#tV$rY8wxYw7D#1swYAxYww)a= Stream real-time inference on camera feed and save results to file. Args: source (str | Path | List[str] | List[Path] | List[np.ndarray] | np.ndarray | torch.Tensor, optional): Source for inference. model (str | Path | torch.nn.Module, optional): Model for inference. *args (Any): Additional arguments for the inference method. **kwargs (Any): Additional keyword arguments for the inference method. Yields: (ultralytics.engine.results.Results): Results objects. NlabelsTparentsexist_okrB)r'r)r(on_predict_starton_predict_batch_startrCon_predict_postprocess_end@@)rTr]rp on_predict_batch_endc3VK|] }|jjz dz"yw)rN)tr-).0rhr8s r: z1BasePredictor.stream_inference..ts"?accDIIo+?s&)zRSpeed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape r}rAz labels/*.txtz labelsz saved to zResults saved to boldon_predict_end);r verboserinfor% setup_modelr6rrusavesave_txtr!rVr#warmupretritonr)bsr}r'r-r.r/rProfiler( run_callbacksrTr]rYrErFrGrpr0rcrangedtspeedr$ write_resultsr StopIterationjoinr*valuescv2 VideoWriterreleasedestroyAllWindowstupleminrfrK save_croprtglobr)r8rur%r r\ profilerspathsim0srr=rmnivrnls` r:rszBasePredictor.stream_inferences^ 99   KKOzz   U # ZZ> (   (:f @P@P Qyy~~!3!3-1YY-?-?)T]]YYbfquYv## !! $ 1B1B1 Y]YcYcYfYftimisist"$( 23R /DIt|TZ 4;;/ 4;;/ 4;;/I   1 2"ll( ( ""#;)B+4Q (B'') A!S__-   99>>  ! ! # 99  ?Y??A KKd 3WTZZq5QaTVT\T\]^]_T`abdfgh  99>>TYY//4993F3FT$--,,^<=>BW[W`W`WiWi"RDsb1f~.j9Q8RSoqA KK+HVT]],K+LQCP Q +,q//Y!!EE %(}> (> (sAZ7G-Z*Y, Z*$AY<3Y9 4Y<9 Z* Z*Z )$Z*C Z-ZAZ*#Z'$Z*+?Z7+GZ7,Y6 1Z*9Y<<Z Z* Z Z* Z$Z*#Z$$Z**Z4/Z7rc pt|xs|jjt|jj||jj |jj |jjd||_|jj|_|jj|j_t|jdr|j(j@r4|jA|jdz |jj|j(j,r|j-tC||j(j*r)|jE|j|jFz ||S)aq Write inference results to a file or directory. Args: i (int): Index of the current image in the batch. p (Path): Path to the current image. im (torch.Tensor): Preprocessed image tensor. s (List[str]): List of result strings. Returns: (str): String with result information. rrANz: z frame (\d+)/rBrrbryz {:g}x{:g} rCr]z.1fms) line_widthboxesr"rim_gpuz.txt) save_confcrops)r! file_name)$rcrKr,rqfrom_imgrZr)countresearchintr!r[moder3formatr0__str__rrr rr$plotr show_boxes show_conf show_labels retina_masksr+rrrstrsave_predicted_imagesname) r8rrr=rstringframematchresults r:rzBasePredictor.write_resultss^ rxx=A DB    " "d&6&6&?&?4CSCSCZCZ 2h FLL&&EIIoqt4E%*CaME 0AFFDLLDUDUY`D`bhijoipfq4rs %,%%rxx|44a--//1V^^%&v||K'@&ERHH 99>>TYY^^%{{99//ii**YY((yy,,#yy55t2a5 + D  99   OOt}}oT2dii>Q>QO R 99     dmmg&=I[I[  \ 99>> IIc!f  99>>  & &t}}qvv'=u E r< save_pathrc|j}|jjdvrt|jjdk(r|jjnd}|j|j dz }||j vr|jjrt|jddtrdn trdnd \}}tjtt|j!|tj"|||j$d |j$d f |j |<|j |j'||jjr*tj(|d |j d|d|yytj(t|j!d|y)z Save video predictions as mp4 or images as jpg at specified path. Args: save_path (Path): Path to save the results. frame (int): Frame number for video mode. >videorqr_framesTr)z.mp4avc1).aviWMV2)rMJPGrBr)filenamefourccfps frameSize/ryz.jpgN)r+r)rrr!r[r*r save_framesrrVrrrrr with_suffixVideoWriter_fourccrKwriteimwrite)r8rrr=r frames_pathsuffixrs r:rz#BasePredictor.save_predicted_imagessn   <<   3 3&*ll&7&77&B$,,""C--Y^^, '2DcN+'2T#tH~"567 '2RU5<<bjj1A#ABu||2vELLv0RZZ 00T"**5E0(OO**4h-h-T$01s1t11$s)1PS1f @t @C @D  c  3 +#+X+r<r)+r rrr4pathlibrtypingrrrrrrnumpyrHrFultralytics.cfgr r ultralytics.datar ultralytics.data.augmentr ultralytics.nn.autobackendr ultralytics.utilsrrrrrrrultralytics.utils.checksrrultralytics.utils.filesrultralytics.utils.torch_utilsrrrrrlr<r:rsYB 33  12.2[[[>2M {+{+r<